As part of this course, you will find and analyze a data set of your own choosing. The project is intentionally open-ended and it is up to you to decide what to analyze and how to do it. We have examined several types of tests in class and will also study multivariate data analysis techniques after the next exam. You could analyze your data set with methods we cover in class or with new techniques that you will learn on your own.
There is no grade on your proposal. Even so, the better you do on your proposal, the smoother sailing you will have on your project. Just don’t worry and panic if you don’t get everything right. The point of the proposal is so that we can develop a good plan for analyzing your data.
When you finish your project, you will turn in a 3–6 page report, plus figures and references. There is no class presentation. Your report (not your proposal) will be evaluated on five equally weighted criteria:
The interpretation of your results. Is there a clearly defined scientific question to which statistics can be fruitfully applied? What is the larger significance of your results?
The appropriateness of your statistical techniques. Did you use the right tools to analyze the data?
The correctness of your results. Did you perform the calculations correctly?
The ambition of the project. If you perform a new type of analysis, one we have not covered in class, you will be rewarded for your extra effort. Likewise, if your project is a large one, you will be rewarded. At the same time, do not make your project unreasonably large; it is a course project, not a dissertation.
The presentation of your results. Are your figures well designed and prepared? Is your report intelligently structured? Is your text concise and well composed?
Your first task is to find a data set to analyze. You may use data from your thesis or dissertation work. You may collect data specifically for this course, which would count towards ambition. You may use published data; there is a wealth of unanalyzed, insufficiently analyzed, and improperly analyzed data in journals.
Once you have found a data set, prepare a one-page write-up of the problem you will work on. In it, you should:
1) Succinctly state the scientific problem to be solved. You should make it clear what broader scientific question your study will address, that is, why the study is scientifically relevant.
2) Clearly state your hypothesis. A hypothesis should be a one-sentence statement about the world that is testable, in other words, a statement that could be shown to be false. If you are testing multiple hypotheses, list them separately. Be sure that your problem is scientifically important; do not pose a hypothesis simply because you know how to test it statistically.
3) Describe the data (nominal, ordinal, etc.; open vs. closed; other considerations) and include a copy of the data, preferably as a text file. If your project examines only a portion of a larger data set, include only the data that you will use. Label everything clearly. If you have not yet collected the data, show me the structure of the data set (the names of the variables, how many samples, etc.). The data file does not count towards the one-page limit.
4) Outline how you plan to analyze the data. Specify the tests or methods you will use and their rationale. State how you will justify assumptions of your chosen tests. If you think we have not discussed appropriate ways of examining your data, talk to me. Soon.
This one-page write-up (plus the data) should be e-mailed to me by 9:00 AM, Wednesday, 1 November. I will return your write-ups shortly, so that you can begin work immediately. Be sure that the subject line is 8370 proposal.